How to Deploy and Run a C-Based AI Model on Target Hardware?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content
2025-02-10 8:37 PM
Hello everyone,
I have successfully set up and run a C-based AI model on my local development environment using the X-CUBE-AI libraries and a Makefile. The setup involves compiling and executing the model on my local CPU, and I am getting the expected output.
Here is a brief overview of my current setup:
- Development Environment: Windows with a MinGW-W64 toolchain.
- Project Structure:
- A makefile to compile the project.
- Source files including main.c, and generated model files located in the model directory.
- X-CUBE-AI libraries located in the cubeai_lib_XX directory.
Now, I am looking to deploy and run this model on my target hardware, which is an STM32 microcontroller. However, I am unsure about the steps needed to transition from running the model on my local CPU to executing it on the target hardware. Unfortunately, I could not find much documentation on this process.
Could anyone provide guidance or resources on:
- How to set up the environment for cross-compilation for STM32?
- How to transfer the compiled application to the STM32 board?
- Any specific configurations or considerations I should be aware of when running the model on STM32?
Any help or pointers to relevant documentation would be greatly appreciated!
Thank you!
- Labels:
-
STM32F7 Series
